Lab 2: ggplot2 package

Registration number: 19BCE1717
Faculty: Prof. Parvathi R
Slot: L55 + L56
Course code: CSE3020

Sections:

Part 1: Survey dataset (data of your choice)
- Preprocessing and data cleaning
- Visualisation using ggplot2
Part 2: MTCars and Midwest dataset (from class)

PART 1: Survey dataset

Preprocessing and data cleaning

Import required package and dataset:

#Packages
library(ggplot2)

## Warning: package 'ggplot2' was built under R version 4.0.2

library(MASS)
library(dplyr)

## Warning: package 'dplyr' was built under R version 4.0.2

## 
## Attaching package: 'dplyr'

## The following object is masked from 'package:MASS':
## 
##     select

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

# Dataset from the MASS package -> survey
# I chose this because visualising the survey based on many attributes provides more options and flexibility to explore ggplot2 package. 
data("survey")
data <- survey
head(data)

##      Sex Wr.Hnd NW.Hnd W.Hnd    Fold Pulse    Clap Exer Smoke Height      M.I
## 1 Female   18.5   18.0 Right  R on L    92    Left Some Never 173.00   Metric
## 2   Male   19.5   20.5  Left  R on L   104    Left None Regul 177.80 Imperial
## 3   Male   18.0   13.3 Right  L on R    87 Neither None Occas     NA     <NA>
## 4   Male   18.8   18.9 Right  R on L    NA Neither None Never 160.00   Metric
## 5   Male   20.0   20.0 Right Neither    35   Right Some Never 165.00   Metric
## 6 Female   18.0   17.7 Right  L on R    64   Right Some Never 172.72 Imperial
##      Age
## 1 18.250
## 2 17.583
## 3 16.917
## 4 20.333
## 5 23.667
## 6 21.000

Exploring the dataset

Structure:

str(data)

## 'data.frame':    237 obs. of  12 variables:
##  $ Sex   : Factor w/ 2 levels "Female","Male": 1 2 2 2 2 1 2 1 2 2 ...
##  $ Wr.Hnd: num  18.5 19.5 18 18.8 20 18 17.7 17 20 18.5 ...
##  $ NW.Hnd: num  18 20.5 13.3 18.9 20 17.7 17.7 17.3 19.5 18.5 ...
##  $ W.Hnd : Factor w/ 2 levels "Left","Right": 2 1 2 2 2 2 2 2 2 2 ...
##  $ Fold  : Factor w/ 3 levels "L on R","Neither",..: 3 3 1 3 2 1 1 3 3 3 ...
##  $ Pulse : int  92 104 87 NA 35 64 83 74 72 90 ...
##  $ Clap  : Factor w/ 3 levels "Left","Neither",..: 1 1 2 2 3 3 3 3 3 3 ...
##  $ Exer  : Factor w/ 3 levels "Freq","None",..: 3 2 2 2 3 3 1 1 3 3 ...
##  $ Smoke : Factor w/ 4 levels "Heavy","Never",..: 2 4 3 2 2 2 2 2 2 2 ...
##  $ Height: num  173 178 NA 160 165 ...
##  $ M.I   : Factor w/ 2 levels "Imperial","Metric": 2 1 NA 2 2 1 1 2 2 2 ...
##  $ Age   : num  18.2 17.6 16.9 20.3 23.7 ...

Dimension:

dim(data)

## [1] 237  12

Columns or attributes:

colnames(data)

##  [1] "Sex"    "Wr.Hnd" "NW.Hnd" "W.Hnd"  "Fold"   "Pulse"  "Clap"   "Exer"  
##  [9] "Smoke"  "Height" "M.I"    "Age"

Data cleaning

print(paste("Number of missing values = ", sum(is.na(data))))

## [1] "Number of missing values =  107"

NOTE: There are many missing values that will be filled up using data imputation techniques of mean, median and mode.

Missing data imputation

print(paste("Mean value of the column Wr.Hnd = ", mean(data$Wr.Hnd,na.rm = TRUE)))

## [1] "Mean value of the column Wr.Hnd =  18.6690677966102"

print(paste("Median value of Wr.Hnd = ", median(data$Wr.Hnd,na.rm = TRUE)))

## [1] "Median value of Wr.Hnd =  18.5"

print(paste("Maximum value of Wr.Hnd = ", max(data$Wr.Hnd,na.rm = TRUE)))

## [1] "Maximum value of Wr.Hnd =  23.2"

print(paste("Minimum value of Wr.Hnd = ", min(data$Wr.Hnd,na.rm = TRUE)))

## [1] "Minimum value of Wr.Hnd =  13"

The mean and median values are very close while min and max values are having a wider difference in magnitude. Hence, the use of mean or median in substituting for a NA value in this column is a good practice. After repeating this for other columns, it was found that mean/median imputation is the best choice for other columns too (when the datatype is int or numberic). I chose Mode for categorical type attributes.

Replace numerical missig values:

# used median value to replace the missing values
data <- data %>%
  mutate(Wr.Hnd = replace(Wr.Hnd, is.na(Wr.Hnd), median(Wr.Hnd, na.rm = TRUE)))
data <- data %>%
  mutate(NW.Hnd = replace(NW.Hnd, is.na(NW.Hnd), median(NW.Hnd, na.rm = TRUE)))
data <- data %>%
  mutate(Pulse = replace(Pulse, is.na(Pulse), median(Pulse, na.rm = TRUE)))

# used mean value to replace the missing values
data <- data %>%
  mutate(Height = replace(Height, is.na(Height), mean(Height, na.rm = TRUE)))
data <- data %>%
  mutate(Age = replace(Age, is.na(Age), mean(Age, na.rm = TRUE)))

Replace categorical missing values:

# Build a function that returns the mode of the column:
get_mode <- function(x){
  distinct_values <- unique(x)
  distinct_tabulate <- tabulate(match(x, distinct_values))
  distinct_values[which.max(distinct_tabulate)]
}
# Used mode values to replace the NA values
data <- data %>% 
  mutate(M.I = if_else(is.na(M.I), get_mode(M.I), M.I))
data <- data %>% 
  mutate(W.Hnd = if_else(is.na(W.Hnd), get_mode(W.Hnd), W.Hnd))
data <- data %>% 
  mutate(Clap = if_else(is.na(Clap), get_mode(Clap), Clap))
data <- data %>% 
  mutate(Smoke = if_else(is.na(Smoke), get_mode(Smoke), Smoke))
data <- data %>% 
  mutate(Exer = if_else(is.na(Exer), get_mode(Exer), Exer))
data <- data %>% 
  mutate(Sex = if_else(is.na(Sex), get_mode(Sex), Sex))

Cleaned data ready for visualisation:

print(paste("Number of missing values = ", sum(is.na(data))))

## [1] "Number of missing values =  0"

Visualisation using ggplot2

Scatterplot + encircle

library(ggalt)

## Warning: package 'ggalt' was built under R version 4.0.2

## Registered S3 methods overwritten by 'ggalt':
##   method                  from   
##   grid.draw.absoluteGrob  ggplot2
##   grobHeight.absoluteGrob ggplot2
##   grobWidth.absoluteGrob  ggplot2
##   grobX.absoluteGrob      ggplot2
##   grobY.absoluteGrob      ggplot2

data_select <- data[data$Age > 18 & 
                            data$Age <= 20 & 
                            data$Height > 150 & 
                            data$Height < 180, ]
gg1<-ggplot(data, aes(x=Height, y=Age)) + 
  geom_point(aes(col=Sex, size=Pulse)) +   # draw points
  geom_smooth(method="loess", se=F) + 
  geom_encircle(aes(x=Height, y=Age), 
                data=data_select, 
                color="red", 
                size=2, 
                expand=0.08) +   # encircle
  labs(subtitle="Height Vs Age", 
       y="Age", 
       x="Height", 
       title="Scatterplot + Encircle", 
       caption="Source: data")
plot(gg1)

## `geom_smooth()` using formula 'y ~ x'

Geom_smooth line

g <- ggplot(data, aes(Wr.Hnd, NW.Hnd))
g + geom_point() + 
  geom_smooth(method="lm", se=F) +
    labs(subtitle="Wr.Hnd vs NW.Hnd", 
       y="Wr.Hnd", 
       x="NW.Hnd", 
       title="Scatterplot with overlapping points", 
       caption="Source: data")

## `geom_smooth()` using formula 'y ~ x'

Jittered points

g <- ggplot(data, aes(Wr.Hnd, NW.Hnd))
g + geom_jitter(width = .5, size=1) +
  labs(subtitle="Survey data: Wr.Hnd vs NW.Hnd", 
       y="Wr.Hnd", 
       x="NW.Hnd", 
       title="Jittered Points")

Scatterplot (counts plot)

# Scatterplot
theme_set(theme_bw())  # pre-set the bw theme.
g <- ggplot(data, aes(Wr.Hnd, NW.Hnd))
g + geom_count(col="tomato3", show.legend=F) +
  labs(subtitle="Survey data: Wr.Hnd vs NW.Hnd", 
       y="Wr.Hnd", 
       x="NW.Hnd", 
       title="Counts Plot")

Bubble Plot

# Bubble Plot
data_select <- data[data$Smoke %in% c("Occas", "Regul"), ]
g <- ggplot(data_select, aes(Height, Age)) + 
  labs(subtitle="Survey data: Height vs Age",
       title="Bubble chart")

g + geom_jitter(aes(col=Smoke, size=Wr.Hnd)) + 
  geom_smooth(aes(col=Smoke), method="lm", se=F)

## `geom_smooth()` using formula 'y ~ x'

Marginal Histogram / Boxplot

# Marginal Histogram / Boxplot
qplot(data$Pulse, geom="histogram")

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

ggplot(data=data, aes(Pulse)) + 
  geom_histogram()

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

qplot(data$Pulse,
      geom="histogram",
      binwidth = 1,
      main = "Histogram for Pulse", 
      xlab = "Age",  
      fill=I("blue"), 
      col=I("red"), 
      alpha=I(.4))

ggplot(data=data, aes(Pulse)) + 
  geom_histogram(breaks=seq(10, 50, by=2), 
                 col="red", 
                 aes(fill=..count..)) +
  scale_fill_gradient("Count", low="green", high="red")+labs(title="Histogram for data", x="Pulse", y="Count")

ggplot(data=data, aes(Pulse)) + 
  geom_histogram(aes(y =..density..), 
                 breaks=seq(10, 50, by = 2), 
                 col="red", 
                 fill="green", 
                 alpha=.2) + 
  geom_density(col=2)

Stacked Bar

#Stacked Bar
g <- ggplot(data, aes(Age)) + scale_fill_brewer(palette = "Spectral")

g + geom_histogram(aes(fill=Smoke), 
                   binwidth = .1, 
                   col="black", 
                   size=.1) +  # change binwidth
  labs(title="Histogram with Auto Binning", 
       subtitle="Smokers across Age")

g + geom_histogram(aes(fill=Smoke), 
                   bins=5, 
                   col="black", 
                   size=.1) +   # change number of bins
  labs(title="Histogram with Fixed Bins", 
       subtitle="Smokers across Age")

g <- ggplot(data, aes(Clap))
g + geom_bar(aes(fill=Smoke), width = 0.5) + 
  theme(axis.text.x = element_text(angle=65, vjust=0.6)) + 
  labs(title="Histogram on Categorical Variable", 
       subtitle="Smokers across various type of clappers")

Density plot

# Density plot
g <- ggplot(data, aes(Pulse))
g + geom_density(aes(fill=factor(Sex)), alpha=0.8) + 
  labs(title="Density plot", 
       subtitle="Pulse grouped by Sex",
       caption="Source: survey data",
       x="Pulse",
       fill="Sex")

Box Plot

# Box Plot
g <- ggplot(data, aes(Smoke, Pulse))
g + geom_boxplot(varwidth=T, fill="plum") + 
  labs(title="Box plot", 
       subtitle="Pulse grouped by Smokers",
       caption="Source: survey data",
       x="Smokers",
       y="Pulse")

Correlation

# correlation plot
library(ggcorrplot)

## Warning: package 'ggcorrplot' was built under R version 4.0.2

# Correlation matrix
corr <- round(cor(data[,c(2,3,6,10,12)]), 1)
corr

##        Wr.Hnd NW.Hnd Pulse Height  Age
## Wr.Hnd    1.0    0.9   0.0    0.6  0.0
## NW.Hnd    0.9    1.0   0.0    0.6  0.1
## Pulse     0.0    0.0   1.0   -0.1 -0.1
## Height    0.6    0.6  -0.1    1.0  0.0
## Age       0.0    0.1  -0.1    0.0  1.0

Plot

# Plot
ggcorrplot(corr)

ggcorrplot(corr, method = "circle")

## Warning: `guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> =
## "none")` instead.

ggcorrplot(corr, hc.order = TRUE, outline.col = "white")

# Types of correlogram layout
# --------------------------------
# Get the lower triangle
ggcorrplot(corr, hc.order = TRUE, type = "lower",
           outline.col = "white")

# Get the upeper triangle
ggcorrplot(corr, hc.order = TRUE, type = "upper",
           outline.col = "white")

# Change colors and theme
# --------------------------------
# Argument colors
ggcorrplot(corr, hc.order = TRUE, type = "lower",
           outline.col = "white",
           ggtheme = ggplot2::theme_gray,
           colors = c("#6D9EC1", "white", "#E46726"))

ggcorrplot(corr, hc.order = TRUE, 
           type = "lower", 
           lab = TRUE, 
           lab_size = 3, 
           method="circle", 
           colors = c("tomato2", "white", "springgreen3"), 
           title="Correlogram of mtcars", 
           ggtheme=theme_bw)

## Warning: `guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> =
## "none")` instead.

Diverging Barcharts

#Diverging bars
data1 = data[c(1:50), ]
data1$Sex <- rownames(data1)  # create new column for car names
data1$Height_z <- round((data1$Height - mean(data1$Height))/sd(data1$Height), 2)  # compute normalized mpg
data1$Height_type <- ifelse(data1$Height_z < 0, "below", "above")  # above / below avg flag
data1 <- data1[order(data1$Height_z), ]  # sort
data1$Sex <- factor(data1$Sex, levels = data1$Sex)  # convert to factor to retain sorted order in plot.

# Diverging Barcharts
ggplot(data1, aes(x=Sex, y=Height_z, label=Height_z)) + 
  geom_bar(stat='identity', aes(fill=Height_type), width=.5)  +
  scale_fill_manual(name="Height", 
                    labels = c("Above Average", "Below Average"), 
                    values = c("above"="#00ba38", "below"="#f8766d")) + 
  labs(subtitle="Normalised Height from 'Survey'", 
       title= "Diverging Bars") + 
  coord_flip()

Diverging Lollipop Chart

# Diverging Lollipop Chart
ggplot(data1, aes(x=Sex, y=Height_z, label=Height_z)) + 
  geom_point(stat='identity', fill="black", size=6)  +
  geom_segment(aes(y = 0, 
                   x = Sex, 
                   yend = Height_z, 
                   xend = Sex), 
               color = "black") +
  geom_text(color="white", size=2) +
  labs(title="Diverging Lollipop Chart", 
       subtitle="Normalized height from 'survey data': Lollipop") + 
  ylim(-2.5, 2.5) +
  coord_flip()

Diverging Dot Plot

#Diverging Dot Plot
ggplot(data1, aes(x=Sex, y=Height_z, label=Height_z)) + 
  geom_point(stat='identity', aes(col=Height_type), size=6)  +
  scale_color_manual(name="Height", 
                     labels = c("Above Average", "Below Average"), 
                     values = c("above"="#00ba38", "below"="#f8766d")) + 
  geom_text(color="white", size=2) +
  labs(title="Diverging Dot Plot", 
       subtitle="Normalized height from 'survey data': Dotplot") + 
  ylim(-2.5, 2.5) +
  coord_flip()

Pie chart

# pie chart
pie <- ggplot(data, aes(x = "", fill = factor(Smoke))) + 
  geom_bar(width = 1) +
  theme(axis.line = element_blank(), 
        plot.title = element_text(hjust=0.5)) + 
  labs(fill="Smoke", 
       x=NULL, 
       y=NULL, 
       title="Pie Chart of Smokers", 
       caption="Source: survey data")

pie + coord_polar(theta = "y", start=0)

Violin Plot

# Violin Plot
g <- ggplot(data, aes(Smoke, Pulse))
g + geom_violin() + 
  labs(title="Violin plot", 
       subtitle="Smokers vs Pulse",
       caption="Source: survey data",
       x="Smokers",
       y="Pulse")

Boxplot

# Boxplot
g <- ggplot(data, aes(Smoke, Pulse))
g + geom_boxplot(varwidth=T, fill="plum") + 
  labs(title="Box plot", 
       subtitle="Pulse grouped by Smokers",
       caption="Source: survey data",
       x="Smokers",
       y="Pulse")

Boxplot

# Boxplot
g <- ggplot(data, aes(Smoke, Pulse))
g + geom_boxplot(aes(fill=factor(Sex))) + 
  theme(axis.text.x = element_text(angle=65, vjust=0.6)) + 
  labs(title="Box plot", 
       subtitle="Pulse grouped by Smokers",
       caption="Source: survey data",
       x="Smokers",
       y="Pulse")

Dot + Box Plot

#Dot + Box Plot
g <- ggplot(data, aes(Smoke, Pulse))
g + geom_boxplot() + 
  geom_dotplot(binaxis='y', 
               stackdir='center', 
               dotsize = .5, 
               fill="red") +
  theme(axis.text.x = element_text(angle=65, vjust=0.6)) + 
  labs(title="Box plot + Dot plot", 
       subtitle="Pulse vs Smokers: Each dot represents 1 row in source data",
       caption="Source: survey data",
       x="Smokers",
       y="Pulse")

## Bin width defaults to 1/30 of the range of the data. Pick better value with `binwidth`.

Treemap

library(treemapify)

## Warning: package 'treemapify' was built under R version 4.0.2

ggplot(data, aes(area=Pulse, fill=Smoke, subgroup=Smoke)) + 
  geom_treemap()

ggplot(data, aes(area=Pulse, fill=Smoke, subgroup=Smoke)) + 
  geom_treemap()+
  #main group bordering
  geom_treemap_subgroup_border()+
  #subgroup heading in white
  geom_treemap_subgroup_text(color="white")+
  #all other group text in black
  geom_treemap_text(aes(label=Clap), color="black")+
  scale_x_continuous(expand = c(0, 0)) +
  scale_y_continuous(expand = c(0, 0)) +
  scale_fill_brewer(palette = "Dark2")

PART 2: MTCars and Midwest dataset (from class)

Import libraries and dataset

library(ggplot2)
theme_set(theme_bw())  # pre-set the bw theme.
data("midwest")
midwest

## # A tibble: 437 × 28
##      PID county    state  area poptotal popdensity popwhite popblack popamerindian
##    <int> <chr>     <chr> <dbl>    <int>      <dbl>    <int>    <int>         <int>
##  1   561 ADAMS     IL    0.052    66090      1271.    63917     1702            98
##  2   562 ALEXANDER IL    0.014    10626       759      7054     3496            19
##  3   563 BOND      IL    0.022    14991       681.    14477      429            35
##  4   564 BOONE     IL    0.017    30806      1812.    29344      127            46
##  5   565 BROWN     IL    0.018     5836       324.     5264      547            14
##  6   566 BUREAU    IL    0.05     35688       714.    35157       50            65
##  7   567 CALHOUN   IL    0.017     5322       313.     5298        1             8
##  8   568 CARROLL   IL    0.027    16805       622.    16519      111            30
##  9   569 CASS      IL    0.024    13437       560.    13384       16             8
## 10   570 CHAMPAIGN IL    0.058   173025      2983.   146506    16559           331
## # … with 427 more rows, and 19 more variables: popasian <int>, popother <int>,
## #   percwhite <dbl>, percblack <dbl>, percamerindan <dbl>, percasian <dbl>,
## #   percother <dbl>, popadults <int>, perchsd <dbl>, percollege <dbl>,
## #   percprof <dbl>, poppovertyknown <int>, percpovertyknown <dbl>,
## #   percbelowpoverty <dbl>, percchildbelowpovert <dbl>, percadultpoverty <dbl>,
## #   percelderlypoverty <dbl>, inmetro <int>, category <chr>

Scatterplot

# Scatterplot
gg <- ggplot(midwest, aes(x=area, y=poptotal)) + 
  geom_point(aes(col=state, size=popdensity)) + 
  geom_smooth(method="loess", se=F) + 
  xlim(c(0, 0.1)) + 
  ylim(c(0, 500000)) + 
  labs(subtitle="Area Vs Population", 
       y="Population", 
       x="Area", 
       title="Scatterplot", 
       caption = "Source: midwest")
plot(gg)

## `geom_smooth()` using formula 'y ~ x'

## Warning: Removed 15 rows containing non-finite values (stat_smooth).

## Warning: Removed 15 rows containing missing values (geom_point).

Scatterplot + Encircle

library(ggalt)
midwest_select <- midwest[midwest$poptotal > 350000 & 
                            midwest$poptotal <= 500000 & 
                            midwest$area > 0.01 & 
                            midwest$area < 0.1, ]
gg1<-ggplot(midwest, aes(x=area, y=poptotal)) + 
  geom_point(aes(col=state, size=popdensity)) +   # draw points
  geom_smooth(method="loess", se=F) + 
  xlim(c(0, 0.1)) + 
  ylim(c(0, 500000)) +   # draw smoothing line
  geom_encircle(aes(x=area, y=poptotal), 
                data=midwest_select, 
                color="red", 
                size=2, 
                expand=0.08) +   # encircle
  labs(subtitle="Area Vs Population", 
       y="Population", 
       x="Area", 
       title="Scatterplot + Encircle", 
       caption="Source: midwest")
plot(gg1)

## `geom_smooth()` using formula 'y ~ x'

## Warning: Removed 15 rows containing non-finite values (stat_smooth).

## Warning: Removed 15 rows containing missing values (geom_point).

Scatterplot with overlapping points

g <- ggplot(midwest, aes(popwhite, popblack))
g + geom_point() + 
  geom_smooth(method="lm", se=F) +
    labs(subtitle="White  vs Black population", 
       y="popwhite", 
       x="popblack", 
       title="Scatterplot with overlapping points", 
       caption="Source: midwest")

## `geom_smooth()` using formula 'y ~ x'

Jittered Points

data(mpg, package="ggplot2")
g <- ggplot(mpg, aes(cty, hwy))
g + geom_jitter(width = .5, size=1) +
  labs(subtitle="mpg: city vs highway mileage", 
       y="hwy", 
       x="cty", 
       title="Jittered Points")

Scatterplot

# Scatterplot
theme_set(theme_bw())  # pre-set the bw theme.
g <- ggplot(mpg, aes(cty, hwy))
g + geom_count(col="tomato3", show.legend=F) +
  labs(subtitle="mpg: city vs highway mileage", 
       y="hwy", 
       x="cty", 
       title="Counts Plot")

Bubble Plot

# Bubble Plot
mpg_select <- mpg[mpg$manufacturer %in% c("audi", "ford", "honda", "hyundai"), ]
g <- ggplot(mpg_select, aes(displ, cty)) + 
  labs(subtitle="mpg: Displacement vs City Mileage",
       title="Bubble chart")

g + geom_jitter(aes(col=manufacturer, size=hwy)) + 
  geom_smooth(aes(col=manufacturer), method="lm", se=F)

## `geom_smooth()` using formula 'y ~ x'

# Marginal Histogram / Boxplot
data(mpg)
qplot(mpg$hwy, geom="histogram")

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

ggplot(data=mpg, aes(mpg$hwy)) + 
  geom_histogram()

## Warning: Use of `mpg$hwy` is discouraged. Use `hwy` instead.

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

qplot(mpg$hwy,
      geom="histogram",
      binwidth = 5,  
      main = "Histogram for hwy", 
      xlab = "Age",  
      fill=I("blue"), 
      col=I("red"), 
      alpha=I(.4),
      xlim=c(10,50))

## Warning: Removed 2 rows containing missing values (geom_bar).

ggplot(data=mpg, aes(mpg$hwy)) + 
  geom_histogram(breaks=seq(10, 50, by=2), 
                 col="red", 
                 aes(fill=..count..)) +
  scale_fill_gradient("Count", low="green", high="red")+labs(title="Histogram for mpg", x="hwy", y="Count")

## Warning: Use of `mpg$hwy` is discouraged. Use `hwy` instead.

ggplot(data=mpg, aes(mpg$hwy)) + 
  geom_histogram(aes(y =..density..), 
                 breaks=seq(10, 50, by = 2), 
                 col="red", 
                 fill="green", 
                 alpha=.2) + 
  geom_density(col=2)

## Warning: Use of `mpg$hwy` is discouraged. Use `hwy` instead.

## Warning: Use of `mpg$hwy` is discouraged. Use `hwy` instead.

Stacked Bar

#Stacked Bar
g <- ggplot(mpg, aes(displ)) + scale_fill_brewer(palette = "Spectral")

g + geom_histogram(aes(fill=class), 
                   binwidth = .1, 
                   col="black", 
                   size=.1) +  # change binwidth
  labs(title="Histogram with Auto Binning", 
       subtitle="Engine Displacement across Vehicle Classes")

g + geom_histogram(aes(fill=class), 
                   bins=5, 
                   col="black", 
                   size=.1) +   # change number of bins
  labs(title="Histogram with Fixed Bins", 
       subtitle="Engine Displacement across Vehicle Classes")

g <- ggplot(mpg, aes(manufacturer))
g + geom_bar(aes(fill=class), width = 0.5) + 
  theme(axis.text.x = element_text(angle=65, vjust=0.6)) + 
  labs(title="Histogram on Categorical Variable", 
       subtitle="Manufacturer across Vehicle Classes")

Density plot

# Density plot
g <- ggplot(mpg, aes(cty))
g + geom_density(aes(fill=factor(cyl)), alpha=0.8) + 
  labs(title="Density plot", 
       subtitle="City Mileage Grouped by Number of cylinders",
       caption="Source: mpg",
       x="City Mileage",
       fill="# Cylinders")

# Box Plot
g <- ggplot(mpg, aes(class, cty))
g + geom_boxplot(varwidth=T, fill="plum") + 
  labs(title="Box plot", 
       subtitle="City Mileage grouped by Class of vehicle",
       caption="Source: mpg",
       x="Class of Vehicle",
       y="City Mileage")

Correlation

# correlation plot
library(ggcorrplot)

# Correlation matrix
data(mtcars)
corr <- round(cor(mtcars), 1)

Plot

# Plot
ggcorrplot(corr)

ggcorrplot(corr, method = "circle")

## Warning: `guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> =
## "none")` instead.

ggcorrplot(corr, hc.order = TRUE, outline.col = "white")

# Types of correlogram layout
# --------------------------------
# Get the lower triangle
ggcorrplot(corr, hc.order = TRUE, type = "lower",
           outline.col = "white")

# Get the upeper triangle
ggcorrplot(corr, hc.order = TRUE, type = "upper",
           outline.col = "white")

# Change colors and theme
# --------------------------------
# Argument colors
ggcorrplot(corr, hc.order = TRUE, type = "lower",
           outline.col = "white",
           ggtheme = ggplot2::theme_gray,
           colors = c("#6D9EC1", "white", "#E46726"))

ggcorrplot(corr, hc.order = TRUE, 
           type = "lower", 
           lab = TRUE, 
           lab_size = 3, 
           method="circle", 
           colors = c("tomato2", "white", "springgreen3"), 
           title="Correlogram of mtcars", 
           ggtheme=theme_bw)

## Warning: `guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> =
## "none")` instead.

Diverging Barcharts

#Diverging bars
data("mtcars")  # load data
mtcars$`car name` <- rownames(mtcars)  # create new column for car names
mtcars$mpg_z <- round((mtcars$mpg - mean(mtcars$mpg))/sd(mtcars$mpg), 2)  # compute normalized mpg
mtcars$mpg_type <- ifelse(mtcars$mpg_z < 0, "below", "above")  # above / below avg flag
mtcars <- mtcars[order(mtcars$mpg_z), ]  # sort
mtcars$`car name` <- factor(mtcars$`car name`, levels = mtcars$`car name`)  # convert to factor to retain sorted order in plot.

# Diverging Barcharts
ggplot(mtcars, aes(x=`car name`, y=mpg_z, label=mpg_z)) + 
  geom_bar(stat='identity', aes(fill=mpg_type), width=.5)  +
  scale_fill_manual(name="Mileage", 
                    labels = c("Above Average", "Below Average"), 
                    values = c("above"="#00ba38", "below"="#f8766d")) + 
  labs(subtitle="Normalised mileage from 'mtcars'", 
       title= "Diverging Bars") + 
  coord_flip()

Diverging Lollipop Chart

# Diverging Lollipop Chart
ggplot(mtcars, aes(x=`car name`, y=mpg_z, label=mpg_z)) + 
  geom_point(stat='identity', fill="black", size=6)  +
  geom_segment(aes(y = 0, 
                   x = `car name`, 
                   yend = mpg_z, 
                   xend = `car name`), 
               color = "black") +
  geom_text(color="white", size=2) +
  labs(title="Diverging Lollipop Chart", 
       subtitle="Normalized mileage from 'mtcars': Lollipop") + 
  ylim(-2.5, 2.5) +
  coord_flip()

Diverging Dot Plot

#Diverging Dot Plot
ggplot(mtcars, aes(x=`car name`, y=mpg_z, label=mpg_z)) + 
  geom_point(stat='identity', aes(col=mpg_type), size=6)  +
  scale_color_manual(name="Mileage", 
                     labels = c("Above Average", "Below Average"), 
                     values = c("above"="#00ba38", "below"="#f8766d")) + 
  geom_text(color="white", size=2) +
  labs(title="Diverging Dot Plot", 
       subtitle="Normalized mileage from 'mtcars': Dotplot") + 
  ylim(-2.5, 2.5) +
  coord_flip()

Pie chart

# pie chart

pie <- ggplot(mpg, aes(x = "", fill = factor(class))) + 
  geom_bar(width = 1) +
  theme(axis.line = element_blank(), 
        plot.title = element_text(hjust=0.5)) + 
  labs(fill="class", 
       x=NULL, 
       y=NULL, 
       title="Pie Chart of class", 
       caption="Source: mpg")

pie + coord_polar(theta = "y", start=0)

Violin Plot

# Violin Plot
g <- ggplot(mpg, aes(class, cty))
g + geom_violin() + 
  labs(title="Violin plot", 
       subtitle="City Mileage vs Class of vehicle",
       caption="Source: mpg",
       x="Class of Vehicle",
       y="City Mileage")

Boxplot

# Boxplot
g <- ggplot(mpg, aes(class, cty))
g + geom_boxplot(varwidth=T, fill="plum") + 
  labs(title="Box plot", 
       subtitle="City Mileage grouped by Class of vehicle",
       caption="Source: mpg",
       x="Class of Vehicle",
       y="City Mileage")

Boxplot

# Boxplot
g <- ggplot(mpg, aes(class, cty))
g + geom_boxplot(aes(fill=factor(cyl))) + 
  theme(axis.text.x = element_text(angle=65, vjust=0.6)) + 
  labs(title="Box plot", 
       subtitle="City Mileage grouped by Class of vehicle",
       caption="Source: mpg",
       x="Class of Vehicle",
       y="City Mileage")

Dot + Box Plot

#Dot + Box Plot
g <- ggplot(mpg, aes(manufacturer, cty))
g + geom_boxplot() + 
  geom_dotplot(binaxis='y', 
               stackdir='center', 
               dotsize = .5, 
               fill="red") +
  theme(axis.text.x = element_text(angle=65, vjust=0.6)) + 
  labs(title="Box plot + Dot plot", 
       subtitle="City Mileage vs Class: Each dot represents 1 row in source data",
       caption="Source: mpg",
       x="Class of Vehicle",
       y="City Mileage")

## Bin width defaults to 1/30 of the range of the data. Pick better value with `binwidth`.

Treemap

proglangs <- read.csv("https://raw.githubusercontent.com/selva86/datasets/master/proglanguages.csv")
library(treemapify)

ggplot(proglangs, aes(area=value, fill=parent, subgroup=parent)) + 
  geom_treemap()

ggplot(proglangs, aes(area=value, fill=parent, subgroup=parent)) + 
  geom_treemap()+
  #main group bordering
  geom_treemap_subgroup_border()+
  #subgroup heading in white
  geom_treemap_subgroup_text(color="white")+
  #all other group text in black
  geom_treemap_text(aes(label=id), color="black")+
  scale_x_continuous(expand = c(0, 0)) +
  scale_y_continuous(expand = c(0, 0)) +
  scale_fill_brewer(palette = "Dark2")

Lab 2: ggplot2 package

Makesh Srinivasan

1/28/2022

Data visualisation

Instructions:

Sections:

PART 1: Survey dataset

Preprocessing and data cleaning

Import required package and dataset:

Exploring the dataset

Data cleaning

Missing data imputation

Cleaned data ready for visualisation:

Visualisation using ggplot2

Scatterplot + encircle

Geom_smooth line

Jittered points

Scatterplot (counts plot)

Bubble Plot

Marginal Histogram / Boxplot

Stacked Bar

Density plot

Box Plot

Correlation

Plot

Diverging Barcharts

Diverging Lollipop Chart

Diverging Dot Plot

Pie chart

Violin Plot

Boxplot

Boxplot

Dot + Box Plot

Treemap

PART 2: MTCars and Midwest dataset (from class)

Import libraries and dataset

Scatterplot

Scatterplot + Encircle

Scatterplot with overlapping points

Jittered Points

Scatterplot

Bubble Plot

Stacked Bar

Density plot

Correlation

Plot

Diverging Barcharts

Diverging Lollipop Chart

Diverging Dot Plot

Pie chart

Violin Plot

Boxplot

Boxplot

Dot + Box Plot

Treemap